Speech Recognition

6 tools in this category

Whisper Web

Whisper Web is an MIT-licensed browser speech-to-text demo built with Transformers.js, supporting local transcription, timestamps and TXT/JSON export.

Whisper Webbrowser speech to textTransformers.js

2690

WhisperX

WhisperX is an open-source long-form speech pipeline that adds VAD batching, language-specific word alignment and optional pyannote speaker diarization to faster-whisper.

WhisperXword alignmentspeaker diarization

3060

WhisperDesktop

WhisperDesktop is a Windows desktop app and DirectCompute implementation for running OpenAI Whisper locally on audio, video, and microphone input. This guide covers setup, models, GPUs, subtitles, privacy, and alternatives.

WhisperDesktopOpenAI Whisperspeech recognition

12010

Buzz

Buzz is a free MIT-licensed desktop app for local Whisper transcription, subtitles, live captions, translation and speaker labeling on macOS, Windows and Linux. This guide compares backends, hardware, privacy, accuracy tests, subtitle QA, CLI automation and cloud alternatives.

BuzzBuzz Captionsoffline transcription

14790

Whisper.cpp

Whisper.cpp is a dependency-light C/C++ implementation of OpenAI Whisper for local transcription, translation, streaming, servers, and embedded apps. This guide covers models, quantization, backends, accuracy, privacy, and deployment.

speech-recognitionfree

2940

Whisper

Whisper is OpenAI's MIT-licensed speech-recognition model family and Python reference implementation for local multilingual transcription and speech-to-English translation.

Whisperspeech recognitionlocal transcription

2910